A comprehensive identification protocol for postcranial bones of Southeast Asian Ruminantia. Part 2: Morphological criteria for small and medium-sized species

Random Forest and Naive Bayes classification of postcranial bones from 228 specimens of 14 Southeast Asian ruminant species yields mean accuracies of 87–86% (family) down to 35–33% (species).

• Why it matters: Morphological identification of small and medium-sized ruminant postcranial elements is difficult in biodiversity-rich continental Southeast Asia, where many osteological traits vary and few are uniquely diagnostic.
• What they did: The authors built an osteological reference framework by describing and scoring characters on an initial specimen set, then applying Random Forest and Naive Bayes to independent bones across Family, Subfamily, Genus, and Species.
• The result: Naive Bayes models were implemented in an interactive web application that supports identification from any combination of observable character states, while results quantify limited species-level discrimination.

AI summary of the abstract · may contain errors · not medical advice · read the paper.